-
根据世界卫生组织最新统计,心理健康问题是极端事件(如自杀)发生的主要原因之一[1-3]。在我国高校,由于学生心理健康问题所引发的杀人、自杀等极端事件也时有发生,给社会、高校和家庭造成了极大的伤害。因此,高校学生心理健康问题是一个极其重要的研究课题[4-8]。高校学生心理健康研究既有传统的基于小规模问卷、量表或实验数据的,也有最近利用大数据技术和理念对大范围样本进行分析的。
在小规模数据分析时候,学者们分析了导致学生心理健康的主要原因,包括家庭因素(如父母离异、家庭暴力、贫困等)、学业压力(如同学关系不融洽、学习成绩差、学习动机不良等)和社会因素等[9]。文献[10]探讨了不同强度体育锻炼对提升高校学生心理健康和心理韧性的效果,通过分析武汉职业技术学院1 546名大一学生,发现中等强度的体育锻炼可有效提升高校学生心理健康和心理韧性。文献[11]在全国8所重点高校开展了“农村和贫困地区专项招生计划学生成长与发展调查”,并从大学经济生活、学业表现、综合表现、心理健康与就学满意度等方面,探讨农村和贫困地区专项招生计划学生的发展。研究发现,专项计划学生经济生活拮据,但综合表现良好,且心理健康处于正常水平。文献[12]基于威廉·邓恩公共政策评估标准,在北京市10所不同类型高校部分本科毕业生中进行了问卷调查,提出了高校家庭经济困难学生资助政策评估标准体系框架,特别强调了要关注政策实施效果中对于孩子心理健康成长的影响。
在大数据时代,人们的日常行为被记录下来,形成了海量的数据,为更加深入地分析心理健康提供了可能,也带来了新的挑战[13]。在高校,一卡通记录了学生食堂刷卡、图书馆进出、图书借阅等信息,为分析学生在校行为轨迹提供了便利。文献[14-15]使用匿名校园卡数据,发现学生的生活越规律,学习成绩越好。文献[16-17]分别基于165名新妈妈的健康数据和她们在Facebook上分享的内容,以及476名抑郁症患者的体检数据和他们发病前一年的Twitter内容[17],建立了机器学习模型,通过社交媒体数据预测产后抑郁症和抑郁症,后者预测的精度可以达到70%。基于微博文本[18]和Instagram照片[19]的研究也被证明可以利用机器学习方法以较高精度识别早期抑郁症患者。文献[4]基于多任务回归和增量回归算法,系统地分析了新浪微博用户,并用于预测五大人格。他们发现,新浪微博用户文本信息与人格特性存在很强的关联性。文献[6]构建了主题矩阵,并利用一种无监督方法对用户的文本进行特征提取,从而能够预测新浪微博的用户是否存在自杀倾向。
受最近教育大数据[14-15]和计算社会经济学[20-22]方法论的启发,本文拟通过分析非受控条件下学生的行为数据,挖掘学生心理健康问题,特别是抑郁症状和学生社交行为之间的关系。本文基于高校学生匿名食堂刷卡数据来构建社交网络,并利用《SCL-90测评量表》测评结果刻画学生的抑郁症状发生水平。分析发现无明显抑郁症状的学生更倾向于与不同的同学共餐(推断社交活跃性更高);有明显抑郁症状的学生则更倾向于单独用餐(推断社会活跃性较低)。
Research on the Influence of College Students' Mental Health on Their Social Network Structure
-
摘要: 高校学生心理健康情况是近年来教育工作者普遍关注的焦点问题。目前尚无利用大规模样本分析学生心理健康对其社交行为影响的报导。该文基于某高校4 955位匿名学生一卡通刷卡数据来构建社交网络,并利用《SCL-90测评量表》测评结果刻画学生的抑郁症状发生水平。分析发现,学生心理健康程度极大地影响其社交网络结构:无明显抑郁症状的学生更倾向于与不同的同学共餐(推断社交活跃性更高);有明显抑郁症状的学生则更倾向于单独用餐(推断社会活跃性较低)。Abstract: In recent years, the mental health of college students has been the focus of educators. There is no large-scale sample to analyze the impact of students' mental health on their social behavior. By analyzing 4 955 anonymous students' card swiping and psychological evaluation data of a university, we construct a social network among students based on their meal card swiping data. Furthermore, based on the data of SCL-90 evaluation scale, we evaluate the depression of students. Through analysis, we find that the degree of depression of students dramatically affects their social network structure. Students without obvious depression share meals with more students (speculating higher social activity), and students with obvious depression prefer to share meals with fewer students (inferring lower social activity).
-
Key words:
- big data /
- depression /
- mental health /
- social networks
-
[1] WHO. Suicide rates data by country[EB/OL]. [2019-12-14]. http://apps.who.int/gho/data. [2] WHO. Suicide rates, crude-data by who region[EB/OL]. [2019-12-15]. http://apps.who.int/gho/data. [3] WHO. Suicide rates, age standardized-data by who region [EB/OL]. [2020-12-15]. http://apps.who.int/gho/data. [4] BAI S, HAO B, LI A, et al. Predicting big five personality traits of microblog users[C]//Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies. Atlanta: IEEE, 2013: 501-508 [5] HU Q, LI A, HENG F, et al. Predicting depression of social media user on different observation windows[C]//2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT). Singapore: IEEE, 2015: 361-364. [6] ZHANG L, HUANG X, LIU T, et al. Using linguistic features to estimate suicide probability of Chinese microblog users[C]//International Conference on Human Centered Computing. Cambodia: Springer, 2014: 549-559 [7] 和红, 罗月. 北京高校大学生抑郁状况及其影响因素研究[J]. 现代预防医学, 2015, 42(7): 1261-1264. HE Hong, LUO Yue. Analysis on depression status and influence factors of university students in Beijing[J]. Modern Preventive Medicine, 2015, 42(7): 1261-1264. [8] 刘琰, 谭曦, 李扬, 等. 大学生抑郁情绪现状及影响因素分析[J]. 中华全科医学, 2015(1): 91-93. LIU Yan, TAN Xi, LI Yang, et al. A survey on depression in college students and influencing factors[J]. Chinese Journal of General Practice, 2015(1): 91-93. [9] 饶芸. 浅谈在杭高校四困生形成原因与对策分析[J]. 中国化工贸易, 2015(2): 164. RAO Yun. A brief discussion on the causes and countermeasures of the formation of the four trapped students in Hangzhou Universities[J]. China Chemical Trade, 2015(2): 164. [10] 胡启权. 不同强度体育锻炼对提升高校学生心理健康和心理韧性的效果评价[J]. 中国学校卫生, 2019(1): 83-85. HU Qi-quan. The effect of increased intensity of physical exercises on mental health and resilience among college students[J]. Chinese Journal of School Health, 2019(1): 83-85. [11] 崔盛, 吴秋翔, 王明鑫. 农村和贫困地区专项招生计划学生发展研究——基于全国8所重点高校的调查[J]. 中国高教研究, 2019(2): 34-40, 66. CUI Sheng, WU Qiu-xiang, WANG Ming-xiang. Study on development of college students recruited under the special admission policies for rural and poor areas: the investigation report of eight elite universities[J]. China Higher Education Research, 2019(2): 34-40, 66. [12] 武立勋. 高校家庭经济困难学生资助政策优化研究——基于公共政策评估理论视角[J]. 北京航空航天大学学报(社会科学版), 2018(2): 99-107. WU Li-xun. Optimization research on financial aid system for university students with financial difficulties based on the theory of public policy evalution[J]. Journal of Being Univerysity of Aeronautics and Astronautics(Social Science Edition), 2018(2): 99-107. [13] 维克托·迈尔-舍恩伯格, 肯尼思·库克耶. 大数据时代: 生活、工作与思维的大变革[M]. 盛杨燕, 周涛, 译. 杭州: 浙江人民出版社, 2013. MAYER-SCHONBERGER V, CAKIVER K. A revolution: That will transform how we live, work, and think[M]. Translated by SHENG Yang-yan, ZHOU Tao. Hangzhou: Zhejiang Renmin Press, 2013. [14] CAO Y, GAO J, LIAN D, et al. Orderliness predicts academic performance: Behavioural analysis on campus lifestyle[J]. Journal of The Royal Society Interface, 2018, 15(146): 20180210. [15] YAO H, LIAN D, CAO Y, et al. Predicting academic performance for college students: A campus behavior perspective[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2019, 10(3): 1-21. [16] DE CHOUDHURY M, COUNTS S, HORVITZ E J, et al. Characterizing and predicting postpartum depression from shared facebook data[C]//Proceedings of the 17th ACM Conference on Computer Supported Cooperative Work & Social Computing. [S.l.]: ACM, 2014: 626-638. [17] DE CHOUDHURY M, GAMON M, COUNTS S, et al. Predicting depression via social media[C]// The 7th International AAAI Conference on Weblogs and Social Media. [S.l.]: AAAI, 2013: 1-10. [18] WANG X, ZHANG C, JI Y, et al. A depression detection model based on sentiment analysis in micro-blog social network[C]//Proceedings of the 2013 Pacific-Asia Conference on Knowledge Discovery and Data Mining. Berlin: Springer, 2013: 201-213. [19] REECE A G, CHRISTOPHER M D. Instagram photos reveal predictive markers of depression[J]. EPJ Data Science, 2017(6): 21. doi: 10.1140/epjds/s13688-017-0110-z [20] 高见, 周涛. 大数据揭示经济发展状况[J]. 电子科技大学学报, 2016, 45(4): 625-633. doi: 10.3969/j.issn.1001-0548.2016.04.015 GAO Jian, ZHOU Tao. Big data reveal the status of economic development[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(4): 625-633. doi: 10.3969/j.issn.1001-0548.2016.04.015 [21] GAO Jian, ZHANG Yi-cheng, ZHOU Tao. Computational socioeconomics[J]. Physics Reports, 2019, 817: 1-104. [22] 周涛. 计算社会经济学——一门正在形成的交叉研究方向[J]. 电子科技大学学报(社科版), 2020, 22(1): 1-4. ZHOU Tao. Computational socioeconomics—An emerging interdisciplinary discipline[J]. Journal of University of Electronic Science and Technology of China (Social Science Edition), 2020, 22(1): 1-4. [23] ZHANG P P, CHEN K, HE Y, et al. Model and empirical study on some collaboration networks[J]. Physica A, 2006, 360: 599-616. doi: 10.1016/j.physa.2005.05.044